Enhanced deep learning model enables accurate alignment measurement across diverse institutional imaging protocols

Abstract

Background: Achieving consistent accuracy in radiographic measurements across different equipment and protocols is challenging. This study evaluates an advanced deep learning (DL) model, building upon a precursor, for its proficiency in generating uniform and precise alignment measurements in full-leg radiographs irrespective of institutional imaging differences.

Methods: The enhanced DL model was trained on over 10,000 radiographs. Utilizing a segmented approach, it separately identified and evaluated regions of interest (ROIs) for the hip, knee, and ankle, subsequently integrating these regions. For external validation, 300 datasets from three distinct institutes with varied imaging protocols and equipment were employed. The study measured seven radiologic parameters: hip-knee-ankle angle, lateral distal femoral angle, medial proximal tibial angle, joint line convergence angle, weight-bearing line ratio, joint line obliquity angle, and lateral distal tibial angle. Measurements by the model were compared with an orthopedic specialist's evaluations using inter-observer and intra-observer intraclass correlation coefficients (ICCs). Additionally, the absolute error percentage in alignment measurements was assessed, and the processing duration for radiograph evaluation was recorded.

Results: The DL model exhibited excellent performance, achieving an inter-observer ICC between 0.936 and 0.997, on par with an orthopedic specialist, and an intra-observer ICC of 1.000. The model's consistency was robust across different institutional imaging protocols. Its accuracy was particularly notable in measuring the hip-knee-ankle angle, with no instances of absolute error exceeding 1.5 degrees. The enhanced model significantly improved processing speed, reducing the time by 30-fold from an initial 10-11 s to 300 ms.

Conclusions: The enhanced DL model demonstrated its ability for accurate, rapid alignment measurements in full-leg radiographs, regardless of protocol variations, signifying its potential for broad clinical and research applicability.

Keywords: Accuracy; Alignment measurement; Deep learning; Full-leg radiographs; Imaging protocol.

Fig. 1

Schematic process of training the DL model. CNN; convolutional neural network

Fig. 2

Examples of full-leg radiographs from Institutes A, B, and C, with each letter representing the corresponding institute

Fig. 3

Bland–Altman plots of the total validation set for each radiologic parameters. a hip-knee-ankle angle. b lateral distal femoral angle. c medial proximal tibial angle. d joint line convergence angle. e weight-bearing line ratio. f joint line obliquity angle. g lateral distal tibial angle